i40e: read the XDP program once per NAPI

Similar to how it's done in the ice driver since 'eb087cd8 ("ice:
propagate xdp_ring onto rx_ring")', read the XDP program once per NAPI
instead of once per descriptor cleaned. I measured an improvement in
throughput of 2% for the AF_XDP xdpsock l2fwd benchmark for zero copy mode
and 1% for copy mode.
Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
Link: https://lore.kernel.org/r/20220623100852.7867-1-ciara.loftus@intel.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/intel/i40e/i40e_txrx.c

@@ -2289,16 +2289,14 @@ int i40e_xmit_xdp_tx_ring(struct xdp_buff *xdp, struct i40e_ring *xdp_ring)
  * i40e_run_xdp - run an XDP program
  * @rx_ring: Rx ring being processed
  * @xdp: XDP buffer containing the frame
+ * @xdp_prog: XDP program to run
  **/
-static int i40e_run_xdp(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
+static int i40e_run_xdp(struct i40e_ring *rx_ring, struct xdp_buff *xdp, struct bpf_prog *xdp_prog)
 {
 	int err, result = I40E_XDP_PASS;
 	struct i40e_ring *xdp_ring;
-	struct bpf_prog *xdp_prog;
 	u32 act;
 
-	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
-
 	if (!xdp_prog)
 		goto xdp_out;
 
@@ -2443,6 +2441,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 	unsigned int offset = rx_ring->rx_offset;
 	struct sk_buff *skb = rx_ring->skb;
 	unsigned int xdp_xmit = 0;
+	struct bpf_prog *xdp_prog;
 	bool failure = false;
 	struct xdp_buff xdp;
 	int xdp_res = 0;
@@ -2452,6 +2451,8 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 #endif
 	xdp_init_buff(&xdp, frame_sz, &rx_ring->xdp_rxq);
 
+	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
+
 	while (likely(total_rx_packets < (unsigned int)budget)) {
 		struct i40e_rx_buffer *rx_buffer;
 		union i40e_rx_desc *rx_desc;
@@ -2512,7 +2513,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 			/* At larger PAGE_SIZE, frame_sz depend on len size */
 			xdp.frame_sz = i40e_rx_frame_truesize(rx_ring, size);
 #endif
-			xdp_res = i40e_run_xdp(rx_ring, &xdp);
+			xdp_res = i40e_run_xdp(rx_ring, &xdp, xdp_prog);
 		}
 
 		if (xdp_res) {

drivers/net/ethernet/intel/i40e/i40e_xsk.c

@@ -143,20 +143,17 @@ int i40e_xsk_pool_setup(struct i40e_vsi *vsi, struct xsk_buff_pool *pool,
  * i40e_run_xdp_zc - Executes an XDP program on an xdp_buff
  * @rx_ring: Rx ring
  * @xdp: xdp_buff used as input to the XDP program
+ * @xdp_prog: XDP program to run
  *
  * Returns any of I40E_XDP_{PASS, CONSUMED, TX, REDIR}
  **/
-static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
+static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp,
+			   struct bpf_prog *xdp_prog)
 {
 	int err, result = I40E_XDP_PASS;
 	struct i40e_ring *xdp_ring;
-	struct bpf_prog *xdp_prog;
 	u32 act;
 
-	/* NB! xdp_prog will always be !NULL, due to the fact that
-	 * this path is enabled by setting an XDP program.
-	 */
-	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 	act = bpf_prog_run_xdp(xdp_prog, xdp);
 
 	if (likely(act == XDP_REDIRECT)) {
@@ -339,9 +336,15 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 	u16 next_to_clean = rx_ring->next_to_clean;
 	u16 count_mask = rx_ring->count - 1;
 	unsigned int xdp_res, xdp_xmit = 0;
+	struct bpf_prog *xdp_prog;
 	bool failure = false;
 	u16 cleaned_count;
 
+	/* NB! xdp_prog will always be !NULL, due to the fact that
+	 * this path is enabled by setting an XDP program.
+	 */
+	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
+
 	while (likely(total_rx_packets < (unsigned int)budget)) {
 		union i40e_rx_desc *rx_desc;
 		unsigned int rx_packets;
@@ -378,7 +381,7 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 		xsk_buff_set_size(bi, size);
 		xsk_buff_dma_sync_for_cpu(bi, rx_ring->xsk_pool);
 
-		xdp_res = i40e_run_xdp_zc(rx_ring, bi);
+		xdp_res = i40e_run_xdp_zc(rx_ring, bi, xdp_prog);
 		i40e_handle_xdp_result_zc(rx_ring, bi, rx_desc, &rx_packets,
 					  &rx_bytes, size, xdp_res, &failure);
 		if (failure)